CN118033461A - Method and device for evaluating battery health state and electronic equipment - Google Patents
Method and device for evaluating battery health state and electronic equipment Download PDFInfo
- Publication number
- CN118033461A CN118033461A CN202410225843.5A CN202410225843A CN118033461A CN 118033461 A CN118033461 A CN 118033461A CN 202410225843 A CN202410225843 A CN 202410225843A CN 118033461 A CN118033461 A CN 118033461A
- Authority
- CN
- China
- Prior art keywords
- lead
- target
- acid battery
- health
- source model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000036541 health Effects 0.000 title claims abstract description 141
- 238000000034 method Methods 0.000 title claims abstract description 58
- 239000002253 acid Substances 0.000 claims abstract description 155
- 238000012549 training Methods 0.000 claims abstract description 86
- 238000007637 random forest analysis Methods 0.000 claims abstract description 56
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 24
- 238000011156 evaluation Methods 0.000 claims abstract description 19
- 238000012360 testing method Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 16
- 238000010277 constant-current charging Methods 0.000 claims description 16
- 238000013210 evaluation model Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 8
- 230000009467 reduction Effects 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 4
- 239000012535 impurity Substances 0.000 claims description 3
- 230000000875 corresponding effect Effects 0.000 description 49
- 230000006870 function Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 230000032683 aging Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000007600 charging Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000003862 health status Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Secondary Cells (AREA)
Abstract
The invention discloses a method and a device for evaluating the health state of a battery and electronic equipment, wherein the method comprises the following steps: determining a feature to be selected related to the state of health of the lead-acid battery according to the incremental capacity expression of the lead-acid battery; determining the importance degree of the features to be selected through a random forest algorithm, and determining target features related to the health state of the lead-acid battery based on the importance degree; constructing a source model of the lead-acid battery based on training data to be used corresponding to the target features, determining a weight coefficient of the source model, and evaluating the health state of the target lead-acid battery based on the source model and the weight coefficient; the source model is a support vector regression model. The technical scheme of the invention realizes the evaluation of the health state of the lead-acid battery through data corresponding to a small amount of characteristics.
Description
Technical Field
The present invention relates to the field of battery management technologies, and in particular, to a method and an apparatus for evaluating a battery state of health, and an electronic device.
Background
Battery management systems are an integral part of battery energy storage systems and play an important role in lead-acid battery pack condition monitoring and operational control. State of health (SOH) assessment of lead-acid batteries is a core function of lead-acid battery management systems. The accurate SOH can help a Battery Management System (BMS) to correctly judge the aging state of the lead-acid Battery, and has important significance for improving the failure prediction performance and ensuring the safe operation of the Battery.
Most of the existing SOH estimation methods still need a large amount of lead-acid battery aging data, and the established model often lacks generalization capability. Therefore, there is a need for an improvement in the existing SOH estimation methods.
Disclosure of Invention
The invention provides a method and a device for evaluating the health state of a battery and electronic equipment, and the method and the device are used for evaluating the health state of a lead-acid battery based on a small amount of characteristic data.
According to an aspect of the present invention, there is provided a method of evaluating a state of health of a battery, including:
determining a feature to be selected related to the state of health of a lead-acid battery according to an incremental capacity expression of the lead-acid battery;
determining the importance degree of the feature to be selected through a random forest algorithm, and determining the target feature related to the health state of the lead-acid battery based on the importance degree;
constructing a source model of the lead-acid battery based on training data to be used corresponding to the target features, determining a weight coefficient of the source model, and evaluating the health state of the target lead-acid battery based on the source model and the weight coefficient;
Wherein the source model is a support vector regression model.
According to another aspect of the present invention, there is provided an evaluation device of a state of health of a battery, including:
The feature to be selected determining module is used for determining the feature to be selected related to the health state of the lead-acid battery according to the incremental capacity expression of the lead-acid battery;
The target feature determining module is used for determining the importance degree of the feature to be selected through a random forest algorithm and determining the target feature related to the health state of the lead-acid battery based on the importance degree;
The health state evaluation module is used for constructing a source model of the lead-acid battery based on training data to be used corresponding to the target characteristics, determining a weight coefficient of the source model, and evaluating the health state of the target lead-acid battery based on the source model and the weight coefficient;
Wherein the source model is a support vector regression model.
According to another aspect of the present invention, there is provided an electronic apparatus including:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of assessing battery state of health according to any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to implement the method for estimating a state of health of a battery according to any of the embodiments of the present invention when executed.
According to the technical scheme, according to the incremental capacity expression of the lead-acid battery, the characteristics to be selected related to the health state of the lead-acid battery are determined; determining the importance degree of the features to be selected through a random forest algorithm, and determining target features related to the health state of the lead-acid battery based on the importance degree; and constructing a source model of the lead-acid battery based on training data to be used corresponding to the target features, determining a weight coefficient of the source model, and evaluating the health state of the target lead-acid battery based on the source model and the weight coefficient. The target characteristics with great influence on the health state of the lead-acid battery are selected as the evaluation basis of the health state of the lead-acid battery through a random forest algorithm, so that the problem that a large amount of battery aging data is still needed in the existing SOH estimation method is solved, and the evaluation of the health state of the target lead-acid battery based on a small amount of data is realized.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for evaluating a battery state of health according to an embodiment of the present invention;
Fig. 2 is a flowchart of a method for evaluating a battery state of health according to a second embodiment of the present invention;
Fig. 3 is a schematic structural diagram of a device for evaluating a battery state of health according to a third embodiment of the present invention;
Fig. 4 shows a schematic diagram of the structure of an electronic device that may be used to implement an embodiment of the invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a method for evaluating a battery state of health according to an embodiment of the present invention, where the method may be performed by a device for evaluating a battery state of health, which may be implemented in hardware and/or software, and the device may be configured in an electronic device. Such as a computer device. As shown in fig. 1, the method includes:
S110, determining the candidate characteristics related to the health state of the lead-acid battery according to the incremental capacity expression of the lead-acid battery.
Wherein the incremental capacity expression of the lead-acid battery is a mathematical expression describing the incremental capacity of the lead-acid battery over successive voltage steps, obtained by comparing the capacity increment during the constant current charging phase with the voltage variation. The feature to be selected may be various features that affect the state of health of the lead acid battery, for example, the feature to be selected may be a constant current charge time of the lead acid battery. Based on the incremental capacity expression of the lead acid battery, various characteristics related to the state of health of the lead acid battery may be determined.
Based on the scheme, according to the incremental capacity expression of the lead-acid battery, determining the candidate characteristics related to the health state of the lead-acid battery comprises the following steps: establishing an incremental capacity expression of the lead-acid battery based on battery capacity and battery voltage, and drawing an incremental capacity curve of the lead-acid battery based on the incremental capacity expression; based on the delta capacity curve, a candidate feature associated with the lead acid battery state of health is determined.
It will be appreciated that the nature of the integrated circuit is such that the constant current charge data is analysed by differential equations, and thus the lead acid battery will be put in a state of constant current charge, and then an incremental capacity expression for the lead acid battery is established based on the differentiation of the battery capacity and the differentiation of the battery voltage. Further acquiring data related to the incremental capacity expression in the lead-acid battery, such as battery capacity data, voltage data and the like, and drawing an incremental capacity curve of the lead-acid battery based on the acquired data. After the incremental capacity curve is drawn, some characteristics capable of describing the battery aging process are extracted from the curve as candidate characteristics.
Illustratively, the delta capacity (INCREMENTAL CAPACITY, IC) is expressed as: Where Q represents the battery capacity and V represents the battery voltage.
Further, after the IC curve is drawn, determining a feature to be selected, where the feature to be selected may be a voltage, a peak area, a peak value, an incremental variance, a fixed voltage increment difference, a constant current charging time, a constant current charging maximum slope, a curve slope at the end of the constant current charging, a curve slope of the constant current charging, a curve area of the constant current charging, a voltage variation amount at a preset time interval, an average voltage, a voltage standard deviation, a voltage average absolute deviation, a maximum voltage difference, a voltage skewness, and a voltage kurtosis, which correspond to the incremental capacity curve.
Specifically, the peak value of the IC curve, the voltage corresponding to the peak value, and the peak area are selected as the features to be selected reflecting the battery state of health, and are denoted as F1-F3. The delta variance of the IC curve, delta difference of two fixed voltages, F4 and F5, respectively, can be preset based on previous studies and experience.
F5＝Da-Db
Wherein D i is IC value; Is the average value of IC; d a and D b are the values of the IC at two fixed voltages, respectively.
In the Constant Current (CC) charging process of the lead-acid battery, the CC charging time, the maximum slope of a CC curve, the slope of the curve at the end of CC charging, the CC charging time of two specific voltages, the voltage change amount at a specific time interval and the curve area in the CC mode are taken as F6-F11 respectively. Characteristics related to the voltage distribution, such as average voltage, standard deviation of voltage, average absolute deviation of voltage, and maximum voltage difference, are selected as F12-F15. Finally, the skewness and kurtosis of the voltage at different periods can also well describe the SOH of the cell. The skewness and kurtosis of the voltages are denoted as F16 and F17, i.e., F1-F17 are both candidate features.
Wherein F16 is voltage bias; f17 is voltage kurtosis; t is the sampling time; sv is the standard deviation of the voltage; vt is the voltage value; Is the average value of the voltage.
And S120, determining the importance degree of the feature to be selected through a random forest algorithm, and determining the target feature related to the health state of the lead-acid battery based on the importance degree.
The target features refer to features which are determined from the features to be selected through a random forest algorithm and have larger influence on the health state of the lead-acid battery.
Specifically, the importance degree of each feature to be selected can be calculated through a random forest algorithm, and the importance degree can be represented through a corresponding importance value. After the importance value is obtained, the features to be selected can be ranked according to the importance value, and can be ranked in descending order according to the importance value of the features, so that a plurality of features to be selected, which are ranked in front, are selected as target features related to the health state of the lead-acid battery.
In the embodiment, the importance of the extracted feature to be selected can be obtained through a random forest algorithm, and the target feature is selected based on the importance, so that feature dimension reduction is realized. When the state of health of the lead-acid battery is evaluated, data corresponding to some features to be selected with high importance are processed, the state of health of the lead-acid battery can be evaluated, the data required to be input for evaluating the state of health is reduced on the basis of ensuring the accuracy of evaluating the state of health, only data corresponding to part of target features are required, and data corresponding to a large number of features to be selected are not required, so that the complexity of calculation is reduced.
In the embodiment of the invention, determining the importance degree of the feature to be selected through a random forest algorithm comprises the following steps: determining a training data set corresponding to a random forest algorithm according to the characteristics to be selected, and training a random forest model to be used based on the training data set to obtain a target random forest model; based on the target random forest model, carrying out importance analysis on each node in the random forest tree to obtain the reduction amount of the impurity before and after splitting each node; and determining the importance degree of the feature to be selected based on the reduction amount of the node corresponding to the feature to be selected.
The training data set may be composed of a data vector containing the feature to be selected and a state of health value of the lead-acid battery corresponding to the data vector. For example, the data vector may be a vector consisting of specific values of voltage and peak area corresponding to the peak value of the IC curve, and the state of health value of the lead-acid battery corresponding to the data vector may be a value that measures the state of health of the lead-acid battery, e.g., a state of health value of 70%. The present embodiment does not limit the number and types of the features to be selected contained in the data vector.
For a detailed example, the data vector may be a vector of voltage v=3 and peak area s=1, and the state of health value of the lead-acid battery may be 60% when the lead-acid battery is at voltage v=3 and peak area s=1.
It should be noted that the data vector may be determined by historical charge and discharge data of the lead-acid battery, and the state of health value of the lead-acid battery may be an observed value, that is, a value measured by the sensor. And training the random forest model to be used by using a plurality of groups of training samples in the training data set to obtain a target random forest model. The random forest model to be used is an initial random forest model which is not subjected to training iteration and model parameter optimization, and the target random forest model can be a random forest model obtained after training is completed.
In an embodiment of the present invention, the training process to be used with the random forest model may be to randomly select samples from a training dataset to construct a new subset of data. Training each tree to be used in the random forest model, wherein each tree corresponds to one data subset, training each tree through the corresponding data subset to obtain the input-output relation of each tree, and forming the target random forest model through each tree after training.
The training dataset is exemplified by the sets Tn, T n＝{(X1,Y1),…,(Xn,Yn)},X∈Rm, Y ε R
Wherein each input vector is x= { X1, X2, …, xj }, X1, X2, …, xj represents a characteristic variable, i.e. a specific value of a feature to be selected, the input vector is a data vector, and Y1...yn is an observed value of a state of health of the lead-acid battery corresponding to the input vector.
After determining the training dataset, it is obtained by random sampling T n Where k is the index of the tree in the random forest. I.e. randomly selecting samples from the training dataset T n to construct a new data subset/>By the subset/>Training a tree in the random forest with index k.
It should also be noted that, during random sampling, each time a sample is selected to be placed in a new subset of data, the sample is placed back in the original data set, making it possible to reselect. This means that the new data set may contain repeated samples, while there may be some samples in the training data set that are missing. Similar operations are performed for other trees in the random forest.
Let p be the number of trees in the random forest, d be the maximum depth of the tree, and L be the ratio of training set to test set. Training and testing all batteries with the same parameters to obtain the input-output relationship of each tree as follows:
Wherein Y k is the output value of the kth tree in the random forest, X m: representing an input vector, comprising m features.
Obtaining average estimated output of random forest, i.e. averaging all tree prediction results in random forest to obtain final prediction output
And constructing a target random forest model based on the process.
In order to determine the importance degree of each feature to be selected, the importance of each tree node in the random forest can be analyzed, and then the importance of the feature to be selected can be determined according to the importance of the node. In random forests, the importance of each feature is determined by calculating its average value that reduces the unrepeace in all trees. For multiple cells, the sum of the importance weights of all features is normalized to:
where f i,j represents the importance of the jth feature in the ith cell and fj represents the sum of the feature j's reduced unrepeacy on all trees in the random forest.
A new index is defined to evaluate the overall performance of each feature, taking into account the differences between the different cells.
Wherein N is the number of the model batteries; Is the overall importance of the j-th feature.
The importance of each feature to be selected in all the cells is obtained through the above calculation, and then the appropriate target feature is evaluated and selected accordingly.
On the basis of the above embodiment, the number of the features to be selected is at least two, and determining the target feature related to the health state of the lead-acid battery based on the importance degree includes: and sorting at least two features to be selected based on the importance degree, and selecting the target feature from the at least two features to be selected based on a sorting result.
S130, constructing a source model of the lead-acid battery based on training data to be used corresponding to the target features, determining a weight coefficient of the source model, and evaluating the health state of the target lead-acid battery based on the source model and the weight coefficient.
The training data to be used corresponding to the target feature may include a specific value of the target feature and a health value of the battery, and the source model is a support vector regression model.
Specifically, the training support vector regression model can be optimized on the basis of the data corresponding to the target features, and the model parameters are obtained to obtain the corresponding source model. Multiple lead-acid batteries with the same parameters can be selected, training is carried out based on corresponding training data to be used to obtain source models, then the weight coefficient of each source model is calculated, and the multiple source models are overlapped to obtain a battery health state evaluation model of the target lead-acid battery. And the state of health of the target lead-acid battery can be evaluated through a battery state of health evaluation model.
According to the technical scheme, according to the incremental capacity expression of the lead-acid battery, the characteristics to be selected related to the health state of the lead-acid battery are determined; determining the importance degree of the features to be selected through a random forest algorithm, and determining target features related to the health state of the lead-acid battery based on the importance degree; and constructing a source model of the lead-acid battery based on training data to be used corresponding to the target features, determining a weight coefficient of the source model, and evaluating the health state of the target lead-acid battery based on the source model and the weight coefficient. The target characteristics with great influence on the health state of the lead-acid battery are selected as the evaluation basis of the health state of the lead-acid battery through a random forest algorithm, so that the problem that a large amount of battery aging data is still needed in the existing SOH estimation method is solved, and the evaluation of the health state of the target lead-acid battery based on a small amount of data is realized.
Example two
Fig. 2 is a flowchart of a method for evaluating a battery state of health according to a second embodiment of the present invention, and the present invention is a preferred embodiment of the above embodiments. As shown in fig. 2, the method includes:
S210, determining the candidate characteristics related to the health state of the lead-acid battery according to the incremental capacity expression of the lead-acid battery.
S220, determining importance degrees of the features to be selected through a random forest algorithm, and determining target features related to the health state of the lead-acid battery based on the importance degrees.
S230, dividing training data to be used corresponding to the target features into a training set to be used and a testing set to be used.
The training data to be used comprises a sample characteristic value and a sample health degree value corresponding to the target characteristic; the sample characteristic value may be a specific value corresponding to the target characteristic, and the sample health degree may be a health state evaluation value of the lead-acid battery when the lead-acid battery is in a state corresponding to the sample characteristic value.
Specifically, some lead-acid batteries can be selected as sample lead-acid batteries, then historical data of the sample lead-acid batteries in the using or running charging process is determined, and the historical data corresponding to the target characteristics is determined from the historical data to form training data to be used.
Illustratively, when the target characteristic includes an IC curve peak, a corresponding historical IC curve peak for the lead-acid battery is obtained, and a state of health value for the battery at that peak, e.g., 80% for the IC curve peak at a and 70% for the IC curve peak at B. Wherein, IC curve peak value is A, B and all belongs to sample characteristic value, and the health degree of battery is 80%, 70% and all belongs to sample health degree value. It should be further noted that the target features may also include a voltage average difference, etc., and the corresponding sample feature value is a specific value corresponding to multiple target features.
The plurality of sample feature values and the sample health degree values constitute training data to be used, and then the training data to be used is divided into training sets to be used and test sets to be used according to a preset division ratio, for example, the number of the training sets to be used is 70%, and the number of the test sets to be used is 30%.
S240, training and testing the source model to be trained respectively through training a training set to be used and training the testing set according to the minimization problem of the source model to be trained, and obtaining the source model.
In the embodiment of the invention, a regression function (i.e. a source model to be trained) can be constructed according to the structural risk minimization principle as follows:
Wherein h (x) is the output variable of the support vector regression (Support Vactor Regression, SVR); omega is a weight vector; phi (x) is a function of x mapping from a low dimensional space to a high dimensional space; b is the deviation. Epsilon is defined as the insensitivity loss coefficient, training sets xd, yd and test sets xt, yt are set (common proportions include 70% training set and 30% test set, or 80% training set and 20% test set, etc.). To find the values of ω and b, the minimization problem is established as follows:
Where T is a transposed symbol
Is constrained by:
to solve for ω and b, it can be transformed into:
Wherein the method comprises the steps of And β i is the lagrange multiplier; k (x d,xt) is a kernel function in SVR.
Since the generated target features are highly correlated with the SOH of the battery, the present invention selects a linear function as the kernel function in the SVR, considering that the kernel function needs to be accurate and easy to calculate.
The expression of the linear kernel function is as follows:
s250, establishing a source model of each lead-acid battery, and training each source model based on target sample data corresponding to the target lead-acid battery.
To enhance the generalization ability of the model, a plurality of lead acid batteries may be selected, and a source model for each respective lead acid battery is built in the manner described above.
The target sample data comprises a target sample characteristic value and a target sample health degree value, which correspond to the target characteristic, in the target lead-acid battery; the target lead-acid battery may be a lead-acid battery whose state of health is to be evaluated, the target sample characteristic value may be a specific value in the target lead-acid battery corresponding to the target characteristic, and the target sample health value may be a health value of the target battery.
Specifically, the target sample data is used as a training sample, and each source model is trained. For example, for each SVR source model hb= { h1, …, HB }, substituting the partial data of the target lead-acid battery, i.e., target sample data t= { (x 1, y 1), …, (xn, yn) }, into each source model as a training set, the output may be expressed as:
Oi,j＝hj(xi)
where i, j represent the sample sequence number and the source model index, respectively.
And carrying out k-fold cross validation on the target model. Then, a SVR model of the target cell was created using a small portion of the experimental data for the target cell, denoted hb+1. Its output is denoted Oi, b+1.
S260, in the training process of the source model, obtaining the weight coefficient of the source model by solving the optimization problem of the source model.
Specifically, after solving the optimization problem, the weight coefficient obtained by each model is as follows:
is constrained by:
wherein a j is a weight coefficient; o i,j is the output of each model; yi is the true value of SOH; b+1 represents an additional model added on the basis of the original B source models. B+2 represents an additional parameter in this optimization problem, typically a bias term introduced in the optimization process or a parameter set to meet certain constraints.
And S270, weighting based on each source model and the weight coefficient corresponding to the source model to obtain the target health degree evaluation model of the target lead-acid battery.
Wherein the target health degree evaluation model refers to a model for health state evaluation of the battery. Specifically, a TS-based SVR model (TS-SVR) is obtained, and the expression is:
hf(x)＝a1h1(x)+…+aB+1hB+1(x)+aB+2
In particular, if a particular source model h is highly correlated with battery health, the magnitude of coefficient a will be large, meaning that h is given a greater weight. On the other hand, if the source model is independent of the battery health, a smaller coefficient is learned, which means that the corresponding model is given a smaller weight.
And S280, taking a feature value to be evaluated, corresponding to the target feature, in the target lead-acid battery as input of the target health degree evaluation model, and obtaining the output target lead-acid battery health state value of the target health degree evaluation model.
Specifically, for a lead-acid battery to be evaluated for the state of health, the parameter value corresponding to the target feature in the battery is the feature value to be evaluated, and is used as the input of the target state of health evaluation model, the model can output the result, that is, the state of health value of the target lead-acid battery, for example, the state of health value of the target lead-acid battery is 80%, which represents the state of health of the target lead-acid battery is 80%.
According to the technical scheme provided by the embodiment of the invention, the to-be-selected characteristics related to the health state of the lead-acid battery are determined according to the incremental capacity expression of the lead-acid battery. Determining importance degree of the features to be selected through a random forest algorithm, determining target features related to the health state of the lead-acid battery based on the importance degree, and dividing training data to be used corresponding to the target features into a training set to be used and a testing set to be used. And respectively training and testing the source model to be trained through the training set to be used and the test set to be used according to the minimization problem of the source model to be trained, so as to obtain the source model. And establishing a source model of each lead-acid battery, and training each source model based on target sample data corresponding to the target lead-acid battery. In the training process of the source model, the weight coefficient of the source model is obtained by solving the optimization problem of the source model. Based on each source model and the weight coefficient corresponding to the source model, the source models corresponding to a plurality of lead-acid batteries are overlapped to obtain a target health degree assessment model for assessing the health degree of the target lead-acid batteries, the problem that the model built by the prior art lacks generalization capability is solved, and the generalization capability of the target health degree assessment model is improved, so that the model can adapt to different battery data.
Example III
Fig. 3 is a schematic structural diagram of a battery state of health evaluation device according to a third embodiment of the present invention. As shown in fig. 3, the apparatus includes:
A feature to be selected determining module 310, configured to determine a feature to be selected related to a health status of a lead-acid battery according to an incremental capacity expression of the lead-acid battery;
a target feature determining module 320, configured to determine an importance degree of the feature to be selected through a random forest algorithm, and determine a target feature related to the health state of the lead-acid battery based on the importance degree;
the health state evaluation module 330 is configured to construct a source model of the lead-acid battery based on training data to be used corresponding to the target feature, determine a weight coefficient of the source model, and evaluate the health state of the target lead-acid battery based on the source model and the weight coefficient;
Wherein the source model is a support vector regression model.
According to the technical scheme, according to the incremental capacity expression of the lead-acid battery, the characteristics to be selected related to the health state of the lead-acid battery are determined; determining the importance degree of the features to be selected through a random forest algorithm, and determining target features related to the health state of the lead-acid battery based on the importance degree; and constructing a source model of the lead-acid battery based on training data to be used corresponding to the target features, determining a weight coefficient of the source model, and evaluating the health state of the target lead-acid battery based on the source model and the weight coefficient. The target characteristics with great influence on the health state of the lead-acid battery are selected as the evaluation basis of the health state of the lead-acid battery through a random forest algorithm, so that the problem that a large amount of battery aging data is still needed in the existing SOH estimation method is solved, and the evaluation of the health state of the target lead-acid battery based on a small amount of data is realized.
On the basis of the above apparatus, the candidate feature determining module 310 includes:
The curve drawing module is used for establishing an incremental capacity expression of the lead-acid battery based on battery capacity and battery voltage, and drawing an incremental capacity curve of the lead-acid battery based on the incremental capacity expression;
and the feature extraction module is used for determining the feature to be selected related to the health state of the lead-acid battery based on the increment capacity curve.
On the basis of the device, the features to be selected comprise:
the increment capacity curve corresponds to at least one of voltage, peak area, peak value, increment variance, fixed voltage increment difference, constant current charging time, constant current charging maximum slope, curve slope at the end of constant current charging, curve slope of constant current charging, curve area of constant current charging, preset time interval voltage variation, average voltage, voltage standard deviation, voltage average absolute deviation, maximum voltage difference, voltage skewness and voltage kurtosis.
On the basis of the above apparatus, the target feature determining module 320 includes:
the target random forest model building module is used for determining a training data set corresponding to a random forest algorithm according to the characteristics to be selected, training a random forest model to be used based on the training data set, and obtaining a target random forest model;
The node importance analysis module is used for carrying out importance analysis on each node in the random forest tree based on the target random forest model to obtain the reduction amount of the impurity before and after splitting of each node;
And the feature importance determining module is used for determining the importance degree of the feature to be selected based on the reduction of the non-purity of the node corresponding to the feature to be selected.
Based on the above apparatus, the number of the features to be selected is at least two, and the target feature determining module 320 includes:
and the feature sorting module is used for sorting at least two features to be selected based on the importance degree, and selecting the target feature from the at least two features to be selected based on a sorting result.
Based on the above-described apparatus, the health status evaluation module 330 includes:
the training data to be used dividing module is used for dividing training data to be used corresponding to the target characteristics into a training set to be used and a testing set to be used; the training data to be used comprises a sample characteristic value and a sample health degree value corresponding to the target characteristic;
And the source model building module is used for respectively training and testing the source model to be trained through training of the training set to be used and training of the testing set according to the minimization problem of the source model to be trained, so as to obtain the source model.
Based on the above device, the lead-acid battery is at least two in number, and the health status evaluation module 330 includes:
The source model retraining module is used for establishing a source model of each lead-acid battery and training each source model based on target sample data corresponding to the target lead-acid battery; the target sample data comprises a target sample characteristic value and a target sample health degree value, wherein the target sample characteristic value and the target sample health degree value correspond to target characteristics in the target lead-acid battery;
and the weight coefficient determining module is used for obtaining the weight coefficient of the source model by solving the optimization problem of the source model in the training process of the source model.
Based on the above-described apparatus, the health status evaluation module 330 includes:
the evaluation model determining module is used for weighting based on each source model and the weight coefficient corresponding to the source model to obtain a target health degree evaluation model of the target lead-acid battery;
And the evaluation output module is used for taking the feature value to be evaluated corresponding to the target feature in the target lead-acid battery as the input of the target health degree evaluation model to obtain the target health degree evaluation model and outputting the health state value of the target lead-acid battery.
The battery state of health assessment device provided by the embodiment of the invention can execute the battery state of health assessment method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 4 shows a schematic diagram of the structure of an electronic device that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 4, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as a method of evaluating the state of health of the battery.
In some embodiments, the method of assessing battery state of health may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the above-described method of assessing battery state of health may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the method of assessing the state of health of the battery in any other suitable way (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method of evaluating a state of health of a battery, comprising:
determining a feature to be selected related to the state of health of a lead-acid battery according to an incremental capacity expression of the lead-acid battery;
determining the importance degree of the feature to be selected through a random forest algorithm, and determining the target feature related to the health state of the lead-acid battery based on the importance degree;
constructing a source model of the lead-acid battery based on training data to be used corresponding to the target features, determining a weight coefficient of the source model, and evaluating the health state of the target lead-acid battery based on the source model and the weight coefficient;
Wherein the source model is a support vector regression model.
2. The method of claim 1, wherein determining the candidate feature related to the state of health of the lead-acid battery based on the incremental capacity expression of the lead-acid battery comprises:
establishing an incremental capacity expression of the lead-acid battery based on battery capacity and battery voltage, and drawing an incremental capacity curve of the lead-acid battery based on the incremental capacity expression;
based on the delta capacity curve, a candidate feature associated with the lead acid battery state of health is determined.
3. The method of claim 2, wherein the feature to be selected comprises:
the increment capacity curve corresponds to at least one of voltage, peak area, peak value, increment variance, fixed voltage increment difference, constant current charging time, constant current charging maximum slope, curve slope at the end of constant current charging, curve slope of constant current charging, curve area of constant current charging, preset time interval voltage variation, average voltage, voltage standard deviation, voltage average absolute deviation, maximum voltage difference, voltage skewness and voltage kurtosis.
4. The method of claim 1, wherein determining the importance level of the feature to be selected by a random forest algorithm comprises:
Determining a training data set corresponding to a random forest algorithm according to the characteristics to be selected, and training a random forest model to be used based on the training data set to obtain a target random forest model;
Based on the target random forest model, carrying out importance analysis on each node in the random forest tree to obtain the reduction amount of the impurity before and after splitting each node;
And determining the importance degree of the feature to be selected based on the reduction amount of the node corresponding to the feature to be selected.
5. The method of claim 1, wherein the number of features to be selected is at least two, and determining the lead-acid battery state-of-health related target feature based on the degree of importance comprises:
and sorting at least two features to be selected based on the importance degree, and selecting the target feature from the at least two features to be selected based on a sorting result.
6. The method of claim 1, wherein constructing a source model of the lead-acid battery based on training data to be used corresponding to the target features comprises:
Dividing training data to be used corresponding to the target features into a training set to be used and a testing set to be used; the training data to be used comprises a sample characteristic value and a sample health degree value corresponding to the target characteristic;
and training and testing the source model to be trained respectively through training by using a training set and training by using the testing set according to the minimization problem of the source model to be trained, so as to obtain the source model.
7. The method of claim 6, wherein the number of lead acid batteries is at least two, and determining the weight coefficient of the source model comprises:
Establishing a source model of each lead-acid battery, and training each source model based on target sample data corresponding to the target lead-acid battery; the target sample data comprises a target sample characteristic value and a target sample health degree value, wherein the target sample characteristic value and the target sample health degree value correspond to target characteristics in the target lead-acid battery;
and in the training process of the source model, obtaining the weight coefficient of the source model by solving the optimization problem of the source model.
8. The method of claim 7, wherein evaluating the state of health of the target lead-acid battery based on the source model and the weight coefficients comprises:
weighting based on each source model and the weight coefficient corresponding to the source model to obtain a target health degree evaluation model of the target lead-acid battery;
and taking the feature value to be evaluated, which corresponds to the target feature, in the target lead-acid battery as the input of the target health degree evaluation model to obtain the health state value of the target lead-acid battery output by the target health degree evaluation model.
9. An evaluation device of a battery state of health, comprising:
The feature to be selected determining module is used for determining the feature to be selected related to the health state of the lead-acid battery according to the incremental capacity expression of the lead-acid battery;
The target feature determining module is used for determining the importance degree of the feature to be selected through a random forest algorithm and determining the target feature related to the health state of the lead-acid battery based on the importance degree;
The health state evaluation module is used for constructing a source model of the lead-acid battery based on training data to be used corresponding to the target characteristics, determining a weight coefficient of the source model, and evaluating the health state of the target lead-acid battery based on the source model and the weight coefficient;
Wherein the source model is a support vector regression model.
10. An electronic device, the electronic device comprising:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of assessing a state of health of a battery of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410225843.5A CN118033461A (en) | 2024-02-29 | 2024-02-29 | Method and device for evaluating battery health state and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410225843.5A CN118033461A (en) | 2024-02-29 | 2024-02-29 | Method and device for evaluating battery health state and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118033461A true CN118033461A (en) | 2024-05-14 |
Family
ID=90987235
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410225843.5A Pending CN118033461A (en) | 2024-02-29 | 2024-02-29 | Method and device for evaluating battery health state and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118033461A (en) |
-
2024
- 2024-02-29 CN CN202410225843.5A patent/CN118033461A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115221795A (en) | Training method, prediction method, device, equipment and medium of capacity prediction model | |
| CN116307215A (en) | Load prediction method, device, equipment and storage medium of power system | |
| CN111025041A (en) | Electric vehicle charging pile monitoring method and system, computer equipment and medium | |
| CN114841619A (en) | State evaluation method and device for isolating switch, electronic equipment and medium | |
| CN115146853A (en) | Method, device and equipment for determining carbon consumption based on electrical carbon factor and storage medium | |
| CN115718265A (en) | Method for correcting battery DC resistance test value, electronic device and storage medium | |
| CN116008827A (en) | Determination method and device for lithium ion battery lithium precipitation potential and electronic equipment | |
| CN116125279A (en) | Method, device, equipment and storage medium for determining battery health state | |
| Guo et al. | Health prognostics of lithium-ion batteries based on universal voltage range features mining and adaptive multi-Gaussian process regression with Harris Hawks optimization algorithm | |
| CN118033461A (en) | Method and device for evaluating battery health state and electronic equipment | |
| CN114879042A (en) | Method and device for predicting partial capacity and discharge capacity of battery cell and electronic equipment | |
| CN115291111B (en) | Training method of battery rest time prediction model and rest time prediction method | |
| CN118131071A (en) | Battery health state determining method and device, electronic equipment and storage medium | |
| CN118151037A (en) | Method, device, equipment and storage medium for evaluating health state of lead-acid battery | |
| CN115754752A (en) | Battery SOC prediction method, device, equipment and storage medium | |
| CN116111562A (en) | Method, device, equipment and storage medium for determining reliability of power distribution network | |
| CN116523051A (en) | Model mixed-precision reasoning method, device, equipment and storage medium | |
| CN116845287A (en) | Method, device, equipment and medium for predicting test data of fuel cell | |
| CN118152806A (en) | Model training method, battery health state estimation method, device and medium | |
| CN117420468A (en) | Battery state evaluation method, device, equipment and storage medium | |
| CN116258395A (en) | Project monitoring scheme attribute weight generation method, project monitoring scheme generation method and device | |
| CN116699444A (en) | Lithium battery SOH detection method, device, equipment and medium based on VMD-ICA | |
| CN115329940A (en) | Recommendation method, device and equipment for convolution algorithm and storage medium | |
| CN117634437A (en) | Method and device for describing current running state of equipment and electronic equipment | |
| CN115792628A (en) | Power battery safety evaluation method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |